Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructive=true/non-idempotent/open-world, so the bar is lower, yet the description adds real value: the required permissions for reads vs writes, the fact that responses and reports are filtered by unique_link_group_id/unique_link_ids, and the machine error-code format (e.g. 'max_uses: max_uses_range'). These are behavioral details not covered by annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a long description, but front-loads the entity definition and then layers on limits, filtering, rights and error format, each sentence carrying distinct information. Appropriate sizing for a 10-action, 17-parameter tool, with only mild redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex destructive multi-action tool with nested objects and no output schema, it covers the entity model, permission requirements, filtering side effects, and error format. The only gap is that return values are not described, but the detailed action enum compensates substantially.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 17 parameters in detail (including the nested changes object and enum values). The description adds little parameter-level meaning beyond the domain framing, so the baseline 3 is correct.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource (sets of unique survey links of form /s/<code>) and the managing verb, and it explicitly distinguishes its scope from the main survey address ('Основной адрес опроса работает как раньше'), separating it from set_quiz_link. An agent can grasp the domain without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It lists all available operations and states the read-vs-write rights model (view_results for reads, settings for changes), which implies when it is usable. However it gives no explicit when-to-use/when-not or routing to sibling tools like set_quiz_link or manage_quiz_passwords. Usage is implied rather than directed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.